go-local-health

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard development tasks using well-known Go ecosystem tools.
  • [COMMAND_EXECUTION]: The skill executes local commands such as go test, golangci-lint, tparse, lazygotest, and gocovsh. These are standard tools for Go development.
  • [DATA_EXPOSURE]: The script reads local go.mod files and package structures to determine the scope of tests and linting. No sensitive data is accessed or transmitted externally.
  • [REMOTE_CODE_EXECUTION]: No remote code execution or automated downloads were detected. The skill explicitly instructs the agent to ask the user before installing any missing tools.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns were found. The instructions focus on tool usage and repository guardrails.
  • [COMMAND_EXECUTION]: The provided bash script (scripts/go-local-health) includes robust input validation for the --scope parameter, checking for whitespace, newlines, and leading dashes to prevent argument injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 05:35 AM
Security Audit — agent-trust-hub — go-local-health